© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 62528
    Prev
    Next
    INDEX
    Explanations

    achievements and recognitions in education and sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    809
    -0.07
    dera
    -0.07
    rade
    -0.07
    ázev
    -0.07
    uppet
    -0.07
    haar
    -0.07
    ifest
    -0.07
    ocate
    -0.07
    poke
    -0.07
    Å©
    -0.07
    POSITIVE LOGITS
     ditch
    0.06
     automát
    0.06
     Club
    0.06
     club
    0.06
     Student
    0.06
    Binder
    0.06
    Selective
    0.06
     McCorm
    0.06
     Kor
    0.06
     ROT
    0.06
    Activations Density 0.014%

    No Known Activations